An algorithm for forensic toolmark comparisons

Forensic toolmark analysis traditionally relies on subjective human judgment, leading to inconsistencies and inaccuracies. The multitude of variables, including angles and directions of mark generation, further complicates comparisons. To address this, we introduce a novel approach leveraging 3D data capturing toolmarks from various angles and directions. Through algorithmic training, we objectively compare toolmark signals, revealing clustering by tool rather than angle or direction. Our method utilizes similarity matrices and density plots to establish thresholds for classification, enabling the derivation of likelihood ratios for new mark pairs. With a cross-validated sensitivity of 98% and specificity of 96%, our approach enhances the reliability of toolmark analysis. While its applicability to diverse tools and factors warrants further exploration, this empirically trained, open-source solution offers forensic examiners a standardized means to objectively compare toolmarks, potentially curbing miscarriages of justice in the legal system.